research
∙
11/21/2022
Learning Low-Rank Representations for Model Compression
Vector Quantization (VQ) is an appealing model compression method to obt...
share
research
∙
04/08/2021
Learning specialized activation functions with the Piecewise Linear Unit
The choice of activation functions is crucial for modern deep neural net...
research
∙
03/29/2021
FixNorm: Dissecting Weight Decay for Training Deep Neural Networks
Weight decay is a widely used technique for training Deep Neural Network...
research
∙
09/02/2019
Towards Flops-constrained Face Recognition
Large scale face recognition is challenging especially when the computat...
research
∙
10/08/2016